{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28958237171173096, "min": 0.28958237171173096, "max": 1.0548489093780518, "count": 23 }, "Pyramids.Policy.Entropy.sum": { "value": 8645.771484375, "min": 8645.771484375, "max": 29315.22265625, "count": 23 }, "Pyramids.Step.mean": { "value": 989974.0, "min": 329943.0, "max": 989974.0, "count": 23 }, "Pyramids.Step.sum": { "value": 989974.0, "min": 329943.0, "max": 989974.0, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5232305526733398, "min": -0.06657027453184128, "max": 0.5490578413009644, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.45809936523438, "min": -5.392192363739014, "max": 152.63807678222656, "count": 23 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005275244824588299, "min": -0.060171883553266525, "max": 0.05366263911128044, "count": 23 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4665180444717407, "min": -16.426923751831055, "max": 13.63031005859375, "count": 23 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.0121951219512, "min": 336.0121951219512, "max": 857.3684210526316, "count": 23 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27553.0, "min": 1245.0, "max": 32580.0, "count": 23 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6639877879401532, "min": -0.01578426145409283, "max": 1.6639877879401532, "count": 23 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.44699861109257, "min": -0.5998019352555275, "max": 145.30139857530594, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6639877879401532, "min": -0.01578426145409283, "max": 1.6639877879401532, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.44699861109257, "min": -0.5998019352555275, "max": 145.30139857530594, "count": 23 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03954192583345192, "min": 0.03954192583345192, "max": 0.21357020499233745, "count": 23 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2424379183430574, "min": 0.32818526588380337, "max": 8.115667789708823, "count": 23 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07024348467607663, "min": 0.06539015013688533, "max": 0.0753518722802868, "count": 23 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9834087854650729, "min": 0.2260556168408604, "max": 1.0703924108335439, "count": 23 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0165466687269517, "min": 0.003167477546513611, "max": 0.016550260572237713, "count": 23 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2316533621773238, "min": 0.009502432639540833, "max": 0.2482539085835657, "count": 23 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.764633126107143e-06, "min": 7.764633126107143e-06, "max": 0.0002024472325176, "count": 23 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010870486376550001, "min": 0.00010870486376550001, "max": 0.0027522940825688, "count": 23 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258817857142856, "min": 0.10258817857142856, "max": 0.1674824, "count": 23 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362344999999999, "min": 0.5024472, "max": 2.3174312, "count": 23 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026855903928571436, "min": 0.00026855903928571436, "max": 0.00675149176, "count": 23 }, "Pyramids.Policy.Beta.sum": { "value": 0.003759826550000001, "min": 0.003759826550000001, "max": 0.09179137688, "count": 23 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011295929551124573, "min": 0.011295929551124573, "max": 0.0242669228464365, "count": 23 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15814301371574402, "min": 0.06691375374794006, "max": 0.3397369086742401, "count": 23 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679117343", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679118850" }, "total": 1506.68317384, "count": 1, "self": 0.47901554700001725, "children": { "run_training.setup": { "total": 0.10210393599982126, "count": 1, "self": 0.10210393599982126 }, "TrainerController.start_learning": { "total": 1506.1020543570003, "count": 1, "self": 0.9616158650956095, "children": { "TrainerController._reset_env": { "total": 6.867991341000106, "count": 1, "self": 6.867991341000106 }, "TrainerController.advance": { "total": 1498.1842388639043, "count": 43688, "self": 1.0039786419233678, "children": { "env_step": { "total": 1072.3498900910913, "count": 43688, "self": 998.1624160332858, "children": { "SubprocessEnvManager._take_step": { "total": 73.61027756790509, "count": 43688, "self": 3.386971066964179, "children": { "TorchPolicy.evaluate": { "total": 70.22330650094091, "count": 42576, "self": 70.22330650094091 } } }, "workers": { "total": 0.577196489900416, "count": 43688, "self": 0.0, "children": { "worker_root": { "total": 1502.738790386949, "count": 43688, "is_parallel": true, "self": 583.8742776928389, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001823362000322959, "count": 1, "is_parallel": true, "self": 0.0005869300002814271, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012364320000415319, "count": 8, "is_parallel": true, "self": 0.0012364320000415319 } } }, "UnityEnvironment.step": { "total": 0.08038274199998341, "count": 1, "is_parallel": true, "self": 0.0005320760001268354, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044064199983040453, "count": 1, "is_parallel": true, "self": 0.00044064199983040453 }, "communicator.exchange": { "total": 0.07784607200028404, "count": 1, "is_parallel": true, "self": 0.07784607200028404 }, "steps_from_proto": { "total": 0.0015639519997421303, "count": 1, "is_parallel": true, "self": 0.00037679599972761935, "children": { "_process_rank_one_or_two_observation": { "total": 0.001187156000014511, "count": 8, "is_parallel": true, "self": 0.001187156000014511 } } } } } } }, "UnityEnvironment.step": { "total": 918.8645126941101, "count": 43687, "is_parallel": true, "self": 21.01443875309451, "children": { "UnityEnvironment._generate_step_input": { "total": 15.375278242044715, "count": 43687, "is_parallel": true, "self": 15.375278242044715 }, "communicator.exchange": { "total": 820.1253519239763, "count": 43687, "is_parallel": true, "self": 820.1253519239763 }, "steps_from_proto": { "total": 62.3494437749946, "count": 43687, "is_parallel": true, "self": 13.40610427876527, "children": { "_process_rank_one_or_two_observation": { "total": 48.94333949622933, "count": 349496, "is_parallel": true, "self": 48.94333949622933 } } } } } } } } } } }, "trainer_advance": { "total": 424.8303701308896, "count": 43688, "self": 1.872440611850834, "children": { "process_trajectory": { "total": 80.72175570103718, "count": 43688, "self": 80.50705321403666, "children": { "RLTrainer._checkpoint": { "total": 0.21470248700052252, "count": 2, "self": 0.21470248700052252 } } }, "_update_policy": { "total": 342.2361738180016, "count": 319, "self": 217.1462128819835, "children": { "TorchPPOOptimizer.update": { "total": 125.08996093601809, "count": 15450, "self": 125.08996093601809 } } } } } } }, "trainer_threads": { "total": 9.720006346469745e-07, "count": 1, "self": 9.720006346469745e-07 }, "TrainerController._save_models": { "total": 0.08820731499963586, "count": 1, "self": 0.0016757880002842285, "children": { "RLTrainer._checkpoint": { "total": 0.08653152699935163, "count": 1, "self": 0.08653152699935163 } } } } } } }